Alvoff Inference - Fast, cheap STT · TTS
AI inference based out of India
35 followers
AI inference based out of India
35 followers
Alvoff Inference provides cheap and reliable API for speech-to-text, text-to-speech based out of India. We aim to be the one stop solution for voice related inference. Our infrastructure is purpose-built for audio workloads, which means low latency and lower cost compared to general-purpose cloud providers. You can signup on the platform and get $5 of inference for free.
how does the pricing actually compare per minute to something like deepgram once you burn through that $5 credit
@bnyamint9fq as per claude:
Deepgram's pay-as-you-go Nova-2 is $0.0043/15s = ~$1.03/hour. Their Growth tier is $0.0036/15s (~$0.86/hour).
So your pricing is roughly 30–37x cheaper than Deepgram for speech-to-text. That ₹500 (~$5.90) free credit gets about 2,458 hours of transcription — it's an enormous amount.
tested the stt endpoint on a noisy podcast clip and it came back clean way faster than i expected for the price. nice to see an api like this coming out of india.
@salime7l8 Thanks for checking out the platform!
Latency on the TTS endpoint was noticeably snappier than what I was getting elsewhere, and the $5 free credit was enough to actually test a real use case. Solid option if you need voice inference without the usual hyperscaler pricing.
@duyguekinnq1t Thanks for checking out the platform! Glad you liked it.
Out of India with infrastructure purpose-built for audio, that's a refreshing angle. Latency on the STT side felt snappy in my quick test, and the $5 credit is enough to properly eval it.
how does the latency actually compare to something like openai's whisper or elevenlabs in real world conditions, not just on paper?
Voice features always felt like something only the big players could pull off, so seeing this come within reach for smaller teams is quietly exciting to me. Nice to watch that door open a little wider.